通过细粒度信息块复用，提升长上下文RAG的效率与准确率。
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
- 将检索块分解为语义单元，分步重用其缓存。
- 在标准快速预填充延迟下，答案准确率平均提升5.3%。
- 适合需要高效处理长文档问答的场景。
近期对检索增强生成（RAG）的优化研究利用块级键值缓存复用以避免处理长检索上下文，提高效率，但粗粒度块中仍存在显著的信息冗余和噪声。本文提出CoinRAG（面向长上下文RAG的上下文化信息块键值缓存复用），在低预填充延迟约束下优化了准确率与效率的权衡关系。其核心思想是：如同拼合小币种积累更大价值，CoinRAG通过两阶段检索识别出检索块中的查询相关语义单元，并将离线计算的细粒度信息块缓存切片与块级上下文无缝整合，形成更语义相关且紧凑的上下文表示。在LongBench多跳问答任务上的广泛评估表明，CoinRAG显著降低运行开销，在标准快速预填充延迟预算下，相比基线模型实现新的帕累托前沿，平均答案质量（F1）提升5.3%。
原文摘要 · Abstract (English)
Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG). The name metaphorically reflects our core mechanism: much like assembling small tokens (or "coins") to accumulate a larger value, CoinRAG compositionally reuses offline-computed, fine-grained nugget caches to form a learned contextual representation efficiently in a more semantically relevant but compact manner. Specifically, instead of full-chunk encoding, CoinRAG identifies query-relevant semantic units within retrieved chunks through two-stage retrieval and seamlessly assembles their sliced KV representations with a chunk-level context. Extensive evaluations on LongBench multi-hop question answering tasks demonstrate that CoinRAG significantly reduces operational costs and outperforms the other baselines with a new Pareto frontier and an average 5.3% relative improvement in answer quality (F1) under a standard fast prefill latency budget.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。